{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F57L4X6VQ5QZ3QD2RM3ZNHA2GK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6ef5d441f2f3bfef01bc8070b21a416605762c7e7594632d20f831aee6c111c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-02T01:40:37Z","title_canon_sha256":"234e8b88171bb81f20cd38dc54a5228c9057a58fe00b812fdf4cf47adc77cf15"},"schema_version":"1.0","source":{"id":"2403.01059","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01059","created_at":"2026-07-05T07:51:15Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01059v1","created_at":"2026-07-05T07:51:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01059","created_at":"2026-07-05T07:51:15Z"},{"alias_kind":"pith_short_12","alias_value":"F57L4X6VQ5QZ","created_at":"2026-07-05T07:51:15Z"},{"alias_kind":"pith_short_16","alias_value":"F57L4X6VQ5QZ3QD2","created_at":"2026-07-05T07:51:15Z"},{"alias_kind":"pith_short_8","alias_value":"F57L4X6V","created_at":"2026-07-05T07:51:15Z"}],"graph_snapshots":[{"event_id":"sha256:f22d42fa8b3c64f17c258150d6b1a493e0b568da068d9f1e5dad7d331191530b","target":"graph","created_at":"2026-07-05T07:51:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.01059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine-learning paradigms such as imitation learning and reinforcement learning can generate highly performant agents in a variety of complex environments. However, commonly used methods require large quantities of data and/or a known reward function. This paper presents a method called Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL) that employs a novel reward structure to improve the performance of imitation-learning agents that have access to only a handful of expert demonstrations. CMZ-DRIL uses reinforcement learning to minimize uncertainty among an ensemble o","authors_text":"Austin Juhl, Nathan Larson, Noah Ford, Ryan W. Gardner","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-02T01:40:37Z","title":"Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01059","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:603f6cefe5c1f18d49829008759c85f0f2f6732ea674a9700e41edf503780c78","target":"record","created_at":"2026-07-05T07:51:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6ef5d441f2f3bfef01bc8070b21a416605762c7e7594632d20f831aee6c111c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-02T01:40:37Z","title_canon_sha256":"234e8b88171bb81f20cd38dc54a5228c9057a58fe00b812fdf4cf47adc77cf15"},"schema_version":"1.0","source":{"id":"2403.01059","kind":"arxiv","version":1}},"canonical_sha256":"2f7ebe5fd587619dc07a8b37969c1a3287eda1f2e3ab9e1b6910dba027669599","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f7ebe5fd587619dc07a8b37969c1a3287eda1f2e3ab9e1b6910dba027669599","first_computed_at":"2026-07-05T07:51:15.905577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:15.905577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fzk2AiOivX8G6Sw9lIebYIqX45Fu5c2Y8J3em7vvSCWXj+e/wM8eVfgmTnr4BFLSCLmy4B0n3gUoVrby7KfbBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:15.906007Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01059","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:603f6cefe5c1f18d49829008759c85f0f2f6732ea674a9700e41edf503780c78","sha256:f22d42fa8b3c64f17c258150d6b1a493e0b568da068d9f1e5dad7d331191530b"],"state_sha256":"a5dba44af3c304e7935b36d613be1d936f6893388453bf7f0119056e0c7a9149"}